您的位置:首页  > 论文页面

GPS轨迹中出行目的提取的一种智能算法

发表时间:2011-06-30  浏览量:1874  下载量:1428
全部作者: 邓中伟,季民河
作者单位: 华东师范大学地理信息科学教育部重点实验室
摘 要: 研究试图从理论高度归纳和定义与出行目的识别相关的语义信息类型(时间、土地利用类、交通行为特征和受访者社会经济属性等),探讨如何通过信息集成实现GPS轨迹数据中出行目的的高效提取,在此基础上提出基于机器学习的通用建模思路。实证案例使用36位上海市居民的被动式GPS交通调查数据,利用C5.0算法分析构建出行目的提取决策树。实验结果表明:综合异源异质相关信息从GPS轨迹数据中提取行程目的具有较高精度(约87.6%),研究方法具有一定的可行性和通用性。
关 键 词: 交通规划;居民出行调查;出行目的;GPS轨迹数据;C5.0
Title: Deducing trip purpose from GPS trajectory data: a machine learning approach
Author: DENG Zhongwei, JI Minhe
Organization: Key Laboratory of Geographic Information Science, Ministry of Education, East China Normal University
Abstract: This paper presents a machine learning approach to derive trip purpose from GPS trajectory data coupled with other relevant data sources. This approach employs a number of attributes (i.e. time stamp and land�use type of trip ends, a set of spatiotemporal indices of travel, and demographic and socioeconomic characteristics of respondents) to construct a decision tree for purpose classification. Each attribute provides partial evidence to the depiction of a given purpose, but this depiction may or may not be monotonic, and none of them can work alone towards the goal. A reasoning procedure using the adaptive boosting technique was designed to explore how these attributes could work together to achieve trip purpose derivation. This technique generated multiple decision trees to improve the classification results through a mechanism of voting from these trees. Each tree was constructed in the depth�first fashion with the root node and the split of subsequent nodes being determined on the basis of the gain�ratio computed for the relevant attributes. This procedure was implemented in the C5.0 machine learning environment with 226 GPS trip records collected from 36 respondents. The experimental results seemed rather promising: using 10 iterations for adaptive boosting, an overall classification accuracy of 87.6% was achieved.
Key words: transportation planning; household travel survey; trip purpose; GPS trajectory data; C5.0
发表期数: 2011年6月第12期
引用格式: 邓中伟,季民河. GPS轨迹中出行目的提取的一种智能算法[J]. 中国科技论文在线精品论文,2011,4(12):1064-1070.
 
0 评论数 0
暂无评论
友情链接